AI For Fraud Detection - The RE•WORK Panel

This week as part of the RE●WORK AI For Fraud detection Summit we are organizing a panel titled “Opportunities & Challenges in Using AI to Detect Fraud Across Industry Verticals” — A multi-talented panelists and an interesting topic, what else can one ask for ? Here is a quick overview (BTW, I was able to get a nice link http://bit.ly/ai-fraud !).

Update : The panel discussions went very well — my notes and link to YouTube video at [http://bit.ly/ai-fraud-panel]

The agenda is very simple — 1st : Introductions, 2nd : A quick page set on the context to think about AI in the Fraud Domain and then the main event — we will hear from our esteemed panelists.

The nuances of Fraud and AI

1. Class imbalance — The class imbalance in fraud (small number of fraud transactions w.r.t non-fraud transactions) makes it interesting. We need to do things like creative sampling techniques, sub-set visualization, selecting appropriate data slices to analyze and so forth, where models in other domains work well without these techniques
2. Dynamic — A more interesting challenge is the fact that we are against human ingenuity (value judgement aside) and fast changing behaviors. You are being probed for incongruences, holes in your processes, the limits that you set or just blindspots. So we need to pay more attention to things like monitoring Data Drift, Model Degradation and Model Refresh
3. Weak Signals — Tied to #2 above, any signal from the outside world about fraud is weak at best. Which in turn requires more advanced model architectures and can result in inscrutable models which in turn necessitates explainability
4. Varied — The fraud domain is varied and each sub-domains have their own interesting twists and nuances — think of fraud models in e-commerce vs AML vs Credit Card vs Identity Theft vs Anomaly Detection

Questions:

1. How does AI improve fraud detection — in a broader perspective ?
2. Do they differ in different verticals ?
3. What are the interesting/effective opportunities of AI in your space ?
4. What does the future look like ? Transformers in Fraud ? New Algorithms ? New platforms ?
5. Questions from Audience

Panel Updates:

I will update the notes from the panel here, later tomorrow …

Cheers & See you all there …